© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43662
    Prev
    Next
    INDEX
    Explanations

    collective [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sembl
    -0.09
    ÑĮÑĤе
    -0.08
    chte
    -0.08
    semb
    -0.07
    phet
    -0.07
     dÃłng
    -0.07
    sembled
    -0.07
    ecess
    -0.07
    eri
    -0.07
    atology
    -0.07
    POSITIVE LOGITS
    æĪĸ个人
    0.11
    ypse
    0.10
    áĥ£áĥłáĥĺ
    0.09
    aneously
    0.09
    ifornia
    0.09
    mente
    0.09
    ânea
    0.08
    anea
    0.08
    raries
    0.08
    ÙĬات
    0.08
    Activations Density 0.028%

    No Known Activations